Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 968 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0166. Min Range: -0.0166

Max Act: 0.0166. Min Act: -0.0002

Data Index: 1425499 (Python Code)

Max Activating Token Index: 154

Text #1

Max Range: 0.0166. Min Range: -0.0166

Max Act: 0.0155. Min Act: -0.0002

Data Index: 211313 (C4 (Web Text))

Max Activating Token Index: 230

Text #2

Max Range: 0.0166. Min Range: -0.0166

Max Act: 0.0155. Min Act: -0.0002

Data Index: 279789 (C4 (Web Text))

Max Activating Token Index: 291

Text #3

Max Range: 0.0166. Min Range: -0.0166

Max Act: 0.0151. Min Act: -0.0003

Data Index: 124538 (C4 (Web Text))

Max Activating Token Index: 225

Text #4

Max Range: 0.0166. Min Range: -0.0166

Max Act: 0.0150. Min Act: -0.0002

Data Index: 921633 (C4 (Web Text))

Max Activating Token Index: 277

Text #5

Max Range: 0.0166. Min Range: -0.0166

Max Act: 0.0149. Min Act: -0.0002

Data Index: 180567 (C4 (Web Text))

Max Activating Token Index: 383

Text #6

Max Range: 0.0166. Min Range: -0.0166

Max Act: 0.0146. Min Act: -0.0002

Data Index: 1278026 (C4 (Web Text))

Max Activating Token Index: 260

Text #7

Max Range: 0.0166. Min Range: -0.0166

Max Act: 0.0146. Min Act: -0.0002

Data Index: 145526 (C4 (Web Text))

Max Activating Token Index: 353

Text #8

Max Range: 0.0166. Min Range: -0.0166

Max Act: 0.0149. Min Act: -0.0003

Data Index: 1301066 (C4 (Web Text))

Max Activating Token Index: 303

Text #9

Max Range: 0.0166. Min Range: -0.0166

Max Act: 0.0145. Min Act: -0.0003

Data Index: 720131 (C4 (Web Text))

Max Activating Token Index: 340

Text #10

Max Range: 0.0166. Min Range: -0.0166

Max Act: 0.0143. Min Act: -0.0002

Data Index: 1632109 (Python Code)

Max Activating Token Index: 762

Text #11

Max Range: 0.0166. Min Range: -0.0166

Max Act: 0.0140. Min Act: -0.0002

Data Index: 1403070 (Python Code)

Max Activating Token Index: 300

Text #12

Max Range: 0.0166. Min Range: -0.0166

Max Act: 0.0141. Min Act: -0.0002

Data Index: 1227923 (C4 (Web Text))

Max Activating Token Index: 636

Text #13

Max Range: 0.0166. Min Range: -0.0166

Max Act: 0.0137. Min Act: -0.0002

Data Index: 531570 (C4 (Web Text))

Max Activating Token Index: 161

Text #14

Max Range: 0.0166. Min Range: -0.0166

Max Act: 0.0140. Min Act: -0.0002

Data Index: 1327285 (C4 (Web Text))

Max Activating Token Index: 193

Text #15

Max Range: 0.0166. Min Range: -0.0166

Max Act: 0.0140. Min Act: -0.0002

Data Index: 1241312 (C4 (Web Text))

Max Activating Token Index: 232

Text #16

Max Range: 0.0166. Min Range: -0.0166

Max Act: 0.0137. Min Act: -0.0003

Data Index: 305959 (C4 (Web Text))

Max Activating Token Index: 156

Text #17

Max Range: 0.0166. Min Range: -0.0166

Max Act: 0.0140. Min Act: -0.0003

Data Index: 87412 (C4 (Web Text))

Max Activating Token Index: 261

Text #18

Max Range: 0.0166. Min Range: -0.0166

Max Act: 0.0137. Min Act: -0.0002

Data Index: 645006 (C4 (Web Text))

Max Activating Token Index: 258

Text #19

Max Range: 0.0166. Min Range: -0.0166

Max Act: 0.0140. Min Act: -0.0002

Data Index: 1498526 (Python Code)

Max Activating Token Index: 701